Quickstart

1. Create a key

Sign in to the console, open API keys and create a key. You’ll see it only once: copy it right away somewhere safe, for example an environment variable.

export BEATRICE_API_KEY="bea_sk_..."

2. Your first request

curl https://api.beatriceai.it/v1/chat/completions 
  -H "Authorization: Bearer $BEATRICE_API_KEY" 
  -H "Content-Type: application/json" 
  -d '{
    "model": "beatrice-flash",
    "messages": [{ "role": "user", "content": "Hi! Introduce yourself in one sentence." }]
  }'

3. With the OpenAI SDK

Just change the base URL and the key.

# pip install openai
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.beatriceai.it/v1", api_key=os.environ["BEATRICE_API_KEY"])

reply = client.chat.completions.create(
    model="beatrice-flash",
    messages=[{"role": "user", "content": "Hi! Introduce yourself in one sentence."}],
)
print(reply.choices[0].message.content)

// npm install openai
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.beatriceai.it/v1',
  apiKey: process.env.BEATRICE_API_KEY,
});

const reply = await client.chat.completions.create({
  model: 'beatrice-flash',
  messages: [{ role: 'user', content: 'Hi! Introduce yourself in one sentence.' }],
});
console.log(reply.choices[0].message.content);

4. Streaming

stream = client.chat.completions.create(
    model="beatrice-flash",
    messages=[{"role": "user", "content": "Tell me about Dante in three lines."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

The model reasons before answering: its reasoning comes in the reasoning_content field, separate from content. Details in Chat completions.